{"id":"https://openalex.org/W4404481310","doi":"https://doi.org/10.1145/3687123.3698287","title":"Text2Seg: Zero-shot Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Models","display_name":"Text2Seg: Zero-shot Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Models","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4404481310","doi":"https://doi.org/10.1145/3687123.3698287"},"language":"en","primary_location":{"id":"doi:10.1145/3687123.3698287","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3687123.3698287","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3687123.3698287","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059624873","display_name":"Jielu Zhang","orcid":"https://orcid.org/0000-0002-4321-0580"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jielu Zhang","raw_affiliation_strings":["University of Georgia, Athens, Georgia, USA"],"affiliations":[{"raw_affiliation_string":"University of Georgia, Athens, Georgia, USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050749778","display_name":"Zhongliang Zhou","orcid":"https://orcid.org/0000-0003-4471-6759"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongliang Zhou","raw_affiliation_strings":["University of Georgia, Athens, Georgia, USA"],"affiliations":[{"raw_affiliation_string":"University of Georgia, Athens, Georgia, USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036007312","display_name":"Gengchen Mai","orcid":"https://orcid.org/0000-0002-7818-7309"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gengchen Mai","raw_affiliation_strings":["University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033865274","display_name":"Mengxuan Hu","orcid":"https://orcid.org/0000-0002-8822-2884"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengxuan Hu","raw_affiliation_strings":["University of Virginia, Charlottesville, Virginia, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, Virginia, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067459053","display_name":"Zihan Guan","orcid":"https://orcid.org/0000-0002-0331-3403"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zihan Guan","raw_affiliation_strings":["University of Virginia, Charlottesville, Virginia, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, Virginia, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359839","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0003-1205-8632"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["University of Virginia, Charlottesville, Virginia, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, Virginia, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060956126","display_name":"Lan Mu","orcid":"https://orcid.org/0000-0003-0199-9509"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lan Mu","raw_affiliation_strings":["University of Georgia, Athens, Georgia, USA"],"affiliations":[{"raw_affiliation_string":"University of Georgia, Athens, Georgia, USA","institution_ids":["https://openalex.org/I165733156"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5059624873"],"corresponding_institution_ids":["https://openalex.org/I165733156"],"apc_list":null,"apc_paid":null,"fwci":5.5687,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96998167,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6876674890518188},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6336710453033447},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6169509291648865},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6130390763282776},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5852224826812744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5629898905754089},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5521692633628845},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5275746583938599},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5126065611839294},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09191876649856567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6876674890518188},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6336710453033447},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6169509291648865},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6130390763282776},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5852224826812744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5629898905754089},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5521692633628845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5275746583938599},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5126065611839294},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09191876649856567},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3687123.3698287","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3687123.3698287","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3687123.3698287","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3687123.3698287","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2793268137","https://openalex.org/W3110908156","https://openalex.org/W4283450732","https://openalex.org/W4286233797","https://openalex.org/W4313032421","https://openalex.org/W4388616070","https://openalex.org/W4390874575","https://openalex.org/W4393161689","https://openalex.org/W4400525589"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Remote":[0],"sensing":[1,65,93],"imagery":[2],"is":[3,112],"vital":[4],"for":[5,22,53,63],"environmental":[6],"and":[7],"land":[8],"use":[9],"monitoring,":[10],"necessitating":[11],"efficient":[12],"segmentation":[13,55,67],"methods.":[14],"While":[15],"deep":[16],"learning":[17],"models":[18,44,81],"have":[19],"become":[20],"standard":[21],"segmentation,":[23,50],"they":[24],"require":[25],"extensive":[26,72],"per-pixel":[27],"annotations,":[28],"which":[29],"are":[30],"often":[31],"scarce.":[32],"High":[33],"intra-dataset":[34],"variance":[35],"also":[36],"limits":[37],"the":[38,99],"transferability":[39],"of":[40],"these":[41],"models.":[42],"Although":[43],"like":[45],"SAM":[46,101],"offer":[47],"zero-shot":[48],"instance-level":[49],"adapting":[51],"them":[52],"semantic":[54,66],"remains":[56],"challenging.":[57],"We":[58],"introduce":[59],"Text2Seg,":[60],"a":[61],"method":[62],"remote":[64,92],"that":[68],"reduces":[69],"dependency":[70],"on":[71,90],"annotations":[73],"by":[74],"automatically":[75],"generating":[76],"prompts":[77],"using":[78],"visual":[79],"foundation":[80],"(VFMs).":[82],"This":[83],"approach":[84],"enhances":[85],"generalization":[86],"across":[87],"datasets.":[88],"Experiments":[89],"four":[91],"datasets":[94],"show":[95],"Text2Seg":[96],"significantly":[97],"outperforms":[98],"vanilla":[100],"model,":[102],"with":[103],"improvements":[104],"ranging":[105],"from":[106],"31%":[107],"to":[108],"225%.":[109],"Our":[110],"code":[111],"available":[113],"at":[114],"https://github.com/Douglas2Code/Text2Seg.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":6}],"updated_date":"2026-03-23T07:41:27.035349","created_date":"2025-10-10T00:00:00"}